© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 5572
    Prev
    Next
    INDEX
    Explanations

    terms related to technology or data connectivity

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various forms of connectivity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Lev
    -0.76
    vard
    -0.75
    gas
    -0.74
    bern
    -0.73
    Cola
    -0.71
    chin
    -0.71
    bra
    -0.70
    BY
    -0.70
    nit
    -0.69
    IELD
    -0.69
    POSITIVE LOGITS
     connectivity
    1.66
     arrang
    0.97
     connections
    0.95
     circuitry
    0.88
     lapt
    0.88
     networks
    0.88
     reconnect
    0.87
     outage
    0.85
     cables
    0.85
     mismatch
    0.85
    Activations Density 0.008%

    No Known Activations